知识粗糙性的粒度原理及其属性约简  

Principle of granularity of knowledge roughness and It’s attribute reduction

作　　者：林镇飚[1] 

机构地区：[1]湛江师范学院教育技术部,广东湛江524048

出　　处：《武汉科技学院学报》2006年第9期31-34,共4页Journal of Wuhan Institute of Science and Technology

摘　　要：经典的粗糙集理论提出知识是有粒度的并定义了知识粗糙度的概念,但它不能完全区分不同信息粒度所表示的信息量。本文从信息论的角度定义了信息粒度,粒度函数和粒度熵等概念,重点研究了知识粗糙性的粒度原理。提出了一种基于条件粒度熵的属性约简的启发式算法,通过例子分析,表明该算法是有效的。The classical rough set theory thinks knowledge is granular and defines the concept of knowledge roughness, but it can not completely distinguish the information from the different knowledge granularity. This paper, from the information theory, the concept of information granularity, granularity function and granularity entropy are defined. Granularity principle of knowledge roughness is studied stressfully. The paper offer a new heuristic attribute reduction algorithm based on conditional granularity entropy ,though running an example, we show that this algorithm is effective.

关 键 词：信息论 属性约简 粒度熵 条件粒度熵 粗糙集 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]